New research paper accepted!

Hot news folks! In my qualification exam I proposed two ideas for extending Locality-Sensitive Hashing to general metric spaces. Readily afterwards I wrote a short paper presenting one of the ideas and early results… and guess what? It has been accepted at the SBBD2013 (Brazilian Symposium on Databases).

K-medoids LSH: a new locality sensitive hashing in general metric space
Eliezer S. Silva, Eduardo Valle

Abstract. The increasing availability of multimedia content poses a challenge for information retrieval researchers. Users want not only have access to multimedia documents, but also make sense of them – the ability of finding specific content in extremely large collections of textual and non-textual documents is paramount. At such large scales, Multimedia Information Retrieval systems must rely on the ability to perform search by similarity efficiently. However, Multimedia Documents are often represented by high-dimensional feature vectors, or by other complex representations in metric spaces. Providing efficient similarity search for that kind of data is extremely challenging. In this article, we explore one of the most cited family of solutions for similarity search, the Locality-Sensitive Hashing (LSH), which is based upon the creation of hashing functions which assign, with higher probability, the same key for data that are similar. LSH is available only for a handful distance functions, but, where available, it has been found to be extremely efficient for architectures with uniform access cost to the data. Most of existing LSH functions are restricted to vector spaces. We propose a novel LSH method for generic metric space based on K-medoids clustering. We present comparison with well established LSH methods in vector spaces and with recent competing new methods for metric spaces. Our early results show promise, but also demonstrate how challenging is to work around those difficulties.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s